Package org.apache.nutch.parse

Examples of org.apache.nutch.parse.ParseImpl

80
81
82
83
84
85
86
87
88
89
90
    Metadata metadata = new Metadata();
    metadata.add(Response.CONTENT_DISPOSITION, "filename=filename.ext");
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);

    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(
      new ParseStatus(), "title", new Outlink[0], metadata)), new Text(
        "http://www.example.com/"), new CrawlDatum(), new Inlinks());

    Assert.assertEquals("content-disposition not detected", "filename.ext", doc.getFieldValue("title"));
  }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
  private void assertContentType(Configuration conf, String source, String expected) throws IndexingException {
    Metadata metadata = new Metadata();
    metadata.add(Response.CONTENT_TYPE, source);
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);
    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(
        new ParseStatus(), "title", new Outlink[0], metadata)), new Text(
        "http://www.example.com/"), new CrawlDatum(), new Inlinks());
    Assert.assertEquals("mime type not detected", expected, doc.getFieldValue("type"));
  }
View Full Code Here
163
164
165
166
167
168
169
      idx = Math.min(MAX_TITLE_LEN, script.length());
      title = script.substring(0, idx);
    }
    ParseData pd = new ParseData(ParseStatus.STATUS_SUCCESS, title, outlinks,
                                 c.getMetadata());
    return ParseResult.createParseResult(c.getUrl(), new ParseImpl(script, pd));
  }
View Full Code Here
103
104
105
106
107
108
109
    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS, title,
                                        outlinks, content.getMetadata(),
                                        metadata);
    parseData.setConf(this.conf);
    return new ParseImpl(text, parseData);
  }
View Full Code Here
104
105
106
107
108
109
110
    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,
                                        metadataCollector.getTitle(),
                                        metadataCollector.getOutlinks(),
                                        contentMeta,
                                        metadataCollector.getData());
    return new ParseImpl(metadataCollector.getText(), parseData);
  }
View Full Code Here
132
133
134
135
136
137
138
    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,
                                        metadataCollector.getTitle(),
                                        metadataCollector.getOutlinks(),
                                        contentMeta,
                                        metadataCollector.getData());
    return new ParseImpl(metadataCollector.getText(), parseData);
  }
View Full Code Here
101
102
103
104
105
106
107
                                              resultTitle, outlinks,
                                              content.getMetadata());
    parseData.setConf(this.conf);

    if (LOG.isTraceEnabled()) { LOG.trace("Zip file parsed sucessfully !!"); }
    return new ParseImpl(resultText, parseData);
  }
View Full Code Here
41
42
43
44
45
46
47
48
49
    String class1 = "NonExistingFilter";
    String class2 = "org.apache.nutch.indexer.basic.BasicIndexingFilter";
    conf.set(IndexingFilters.INDEXINGFILTER_ORDER, class1 + " " + class2);

    IndexingFilters filters = new IndexingFilters(conf);
    filters.filter(new Document(), new ParseImpl("text", new ParseData(
        new ParseStatus(), "title", new Outlink[0], new Metadata())), new Text(
        "http://www.example.com/"), new CrawlDatum(), new Inlinks());
  }
View Full Code Here
197
198
199
200
201
202
203
        // }

        ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS,
                contentTitle.toString(), outlinks, content.getMetadata());
        parseData.setConf(this.conf);
        return new ParseImpl(indexText.toString(), parseData);
    }
View Full Code Here
132
133
134
135
136
137
138
    Outlink[] outlinks = OutlinkExtractor.getOutlinks(text, getConf());

    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS, title,
                                        outlinks, content.getMetadata());
    parseData.setConf(this.conf);
    return new ParseImpl(text, parseData);
  }
View Full Code Here
TOP

Related Classes of org.apache.nutch.parse.ParseImpl

  • org.apache.nutch.crawl.TextProfileSignature
  • org.apache.nutch.indexer.anchor.TestAnchorIndexingFilter
  • org.apache.nutch.indexer.basic.TestBasicIndexingFilter
  • org.apache.nutch.indexer.field.BasicFields$Extractor
  • org.apache.nutch.indexer.IndexerMapReduce
  • org.apache.nutch.indexer.more.TestMoreIndexingFilter
  • org.apache.nutch.indexer.staticfield.TestStaticFieldIndexerTest
  • org.apache.nutch.indexer.TestIndexingFilters
  • org.apache.nutch.parse.ext.ExtParser
  • org.apache.nutch.parse.ext.WaxExtParser
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.